Google has released version 1.0 of the Google Gen AI SDK for Kotlin (google-genai-kotlin), a Kotlin Multiplatform (KMP) library that provides idiomatic access to Gemini models.

The SDK eliminates the need for raw HTTP clients or Java bridge libraries by offering Kotlin-native features: Coroutines, Flow streaming, and immutable data classes with named/default parameters.

It provides a unified interface for both the Gemini Developer API (Google AI Studio) and the Gemini Enterprise Agent Platform (Google Cloud) with minimal configuration.

The library is published on Maven Central under com.google.genai:google-genai-kotlin and supports JVM, Android, and multiplatform projects.

Core capabilities include unary and streaming text generation via generateContent and generateContentStream returning Flow, multi-turn chat management through a dedicated chats service that maintains context and handles function calling, and multimodal analysis with Google Search Grounding for factual verification.

The SDK also supports the Gemini 3 image generation family for creating and conversationally editing images, and real-time bidirectional interactions via Gemini Live using persistent WebSocket connections (client.

live.connect).

For agentic workflows, developers can pass structured JSON schemas via FunctionDeclaration, with Automatic Function Calling (AFC) available in the chat service to transparently invoke declared functions.

The 1.0 release targets Kotlin developers building backend services (Ktor, Spring Boot, Quarkus, Micronaut) and mobile applications. Resources include the GitHub repository (github.

com/googleapis/kotlin-genai), sample suite, and issue tracking.